Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Pointer: Drive Your Real Chrome

    1

    Let your agent click, type and read pages in your own Chrome, with your logins, while a visible pointer shows every move. Works with Claude Code, Cursor, Codex, OpenCode and more. Free and open source.

    Free

    Security scanned
    Pointer: Drive Your Real Chrome

    Pointer: Drive Your Real Chrome

    Example session with this skill installed

    Use my browser to open Hacker News and take me to the comments of the most discussed story on the front page.

    • Read your context and instructions
    • Compiled the pointer

    Summary

    Opened Hacker News in a background tab of your Chrome, found the story with the most comments (483), and opened its discussion. You were never pulled away from your own tab; the agent's tab sits in a tab group named after the agent.

    The session

    These are the real commands and Pointer's real output (the MCP tools return the same text).

    $ pointer open news.ycombinator.com
    opened tab 1338347483 in the background: https://news.ycombinator.com/
    
    $ pointer find "comments"
    - link "comments" [ref=e5] href="/newcomments"
    - link "41 comments" [ref=e17] href="/item?id=50268380"
    - link "483 comments" [ref=e24] href="/item?id=50261319"
    - link "22 comments" [ref=e31] href="/item?id=50234796"
    - link "263 comments" [ref=e38] href="/item?id=50261998"
    - link "116 comments" [ref=e45] href="/item?id=50264857"
    - link "154 comments" [ref=e52] href="/item?id=50265609"
    
    $ pointer click e24
    clicked link "483 comments" → https://news.ycombinator.com/item?id=50261319
    new page, current view:
    url: https://news.ycombinator.com/item?id=50261319
    title: agent · Genie 4 | Hacker News
    view: 0% down · 0 elements above, 2891 below (scroll, find, or snapshot scope "all")
    - link "Hacker News" [ref=e2]
    - link "new" [ref=e3]
    - link "comments" [ref=e5]
    ...
    

    What happened on screen

    StepWhat you saw in Chrome
    openA new tab appeared in the agent's tab group, in the background
    findNothing moved: find reads the page and returns short refs
    click e24The cursor slid to "483 comments" with a click · 483 comments label, rippled, and the discussion opened

    Every action reports only what changed, so the agent did not need another full snapshot after the click.

    Result

    The discussion of

    Genie 4 (483 comments) is open in the agent's tab. Say pointer focus (or ask the agent) to bring it to the front, or pointer close when you are done; the agent never closes your own tabs.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Pointer lets an AI coding agent use the Chrome you already have open: your profile, your cookies, your logged-in pages. Every action is drawn on screen. Before a click lands, a cursor slides to the target with a label like click · Sign Up, so you can watch what the agent does and stop it at any time.

    What the skill does

    This skill teaches your agent when and how to use Pointer safely:

    • Snapshot, act, read the change. The agent lists what is on screen as short refs (e3, e14), acts on a ref, and gets back only what changed. A six-step task uses about 2,400 tokens of tool output.
    • Real input. Clicks and keys are trusted browser events, so React apps, hover menus and pointer checks behave as they do for a person.
    • Stays out of your way. The agent works in background tabs, grouped and labelled with its name, and never pulls you away from what you are doing.
    • Safe by default. It confirms before purchases, sending messages, deleting or posting; never types passwords or card numbers; answers dialogs only with your yes; and stops when you press Esc or click in its tab.
    • Debugging tools. Console errors, network requests, screenshots, responsive viewports and a layout checker for overflow and spacing bugs.

    First use

    Pointer has two free parts. On first use the skill walks your agent through setup:

    1. Install the command: npm install -g @longvo2k/pointer (or the installer script).
    2. Add the Pointer extension from the Chrome Web Store (one click, by you).
    3. Optional: register the MCP server so the agent gets Pointer's tools directly.

    Good for

    • Trying a signup or checkout flow and stopping before payment
    • Checking a page that needs your login
    • Filling forms and clicking through admin panels
    • Debugging a UI with real console and network data
    • Live demos, with on-screen captions for people watching

    Open source

    MIT licensed, no telemetry, and it only talks to 127.0.0.1. Source, issues and docs: https://github.com/longvo2k/pointer

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Workflow Automation.

    Cannot drive chrome:// URLs or the Web Store. Does not traverse iframes/shadow roots. Requires manual extension installation. Single agent connection limit.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 20 days ago

    • Free with an Agensi account

    Software
    Google ChromePointer extensionNode.js 18+@longvo2k/pointer

    Both are free: the extension from the Chrome Web Store and the package from npm.

    Permissions

    Terminal / Shell
    Network Access
    Browser
    Listed20 days ago

    What's inside

    Frequently Asked Questions

    Every action is visible: a pointer moves to the target and labels it before the click lands. Press Esc, click in the agent's tab, or press Alt+Shift+S to stop it; it stays stopped until you allow it to continue. The skill tells the agent to confirm before purchases, messages, posts or deletes, and never to type passwords or card numbers. Pointer talks only to 127.0.0.1 and has no telemetry.

    The skill itself: a SKILL.md that teaches your agent how to use Pointer safely, and a small wrapper script. Pointer (the command, its MCP server and the Chrome extension) is free and installed separately; on first use the skill walks your agent through installing it from npm and the Chrome Web Store.

    Yes. The agent works in background tabs, grouped and labelled with its name, and never switches your tab, window or Chrome profile. Bring its tab forward any time to watch. While it is acting, Chrome shows a banner that the browser is being debugged; that is expected.

    No. The agent reads the page as a short list of what is on screen, each element with a ref like e14, and acts on those refs. Refs come from the live page each time, so a redesign does not break a saved script. Each action reports only what changed, which keeps token use low.

    It cannot drive chrome:// pages, the Chrome Web Store or PDF viewers, and it does not look inside iframes or shadow roots. One agent connection works at a time. When a password manager puts its own frame on a page, Chrome limits input there: Pointer falls back to page events for clicks and typing, but file upload is not possible until that popup is closed.

    Any agent that reads SKILL.md files can use the skill, and Pointer itself works with any MCP client (Claude Code, Cursor, Codex, OpenCode and others) or any agent that can run shell commands, through the pointer CLI. It needs Google Chrome and Node.js 18 or newer.

    New in Workflow Automation

    Free